Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    部部长
    -0.07
     Lag
    -0.07
    إست
    -0.07
     dressing
    -0.06
    嵁
    -0.06
     agr
    -0.06
    崮
    -0.06
    放
    -0.06
    洿
    -0.06
    _ARGS
    -0.06
    POSITIVE LOGITS
    𝙽
    0.07
    ║
    0.07
    ตรวจสอบ
    0.07
     noteworthy
    0.07
    けれ
    0.07
     tylko
    0.07
    优秀
    0.06
    $_
    0.06
    nehmer
    0.06
     yaptır
    0.06
    Act Density 0.001%

    No Known Activations